Advertisement

How to Develop Artificial Intelligence Applications

  • Angel Alberich-BayarriEmail author
  • Ana Jiménez Pastor
  • Rafael López González
  • Fabio García Castro
Chapter

Abstract

If there is a field where AI is introducing disruptive innovations, it is healthcare, where doctors have to handle a large set of information in every clinical episode. AI developments have demonstrated to be highly specific, being useful to solve repetitive and rule-driven problems without clinical context with human-like performance, and must be understood more as a complement than a substitute of the radiologist. The quantity and heterogeneity of information to be evaluated by radiologists’ mind during the image interpretation process are high. Radiology is not only about image recognition but a high amount of contextual information. In this chapter, the resources needed to implement a successful AI solution in radiology are detailed. All this knowledge must be embraced by the radiological community in order to obtain efficient applications that allow to improve their work, not considering the technology as a threat but as the main driver of opportunities for the future specialists.

Keywords

Artificial intelligence Imaging biomarkers Structured report Convolutional neural network Data science High-performance computing Graphics processing unit Data annotation Training Testing 

References

  1. 1.
    LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86:2278–324.CrossRefGoogle Scholar
  2. 2.
    Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems. 2012:1097-1105.Google Scholar
  3. 3.
    Hype cycle for emerging technologies 2017. 15-08-2017. www.gartner.com. Accessed 1 May 2018.
  4. 4.
    Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging. Radiographics. 2017:160130–11. Google Scholar
  5. 5.
    Alberich-Bayarri A. Image interpretation. In: Medical radiology. Berlin: Springer; 2017.Google Scholar
  6. 6.
    Lakhani P, Prater AB, Hutson RK, et al. Machine learning in radiology: applications beyond image interpretation. J Am Coll Radiol. 2017:1–10.Google Scholar
  7. 7.
    Fohr D, Mella O, Illina I. New paradigm in speech recognition: deep neural networks. In: IEEE international conference on information systems and economic intelligence, Apr 2017, Marrakech, Morocco. 2017.Google Scholar
  8. 8.
    Cai T, Giannopoulos AA, Yu S, et al. Natural language processing technologies in radiology research and applications. Radiographics. 2016;36:176–91.CrossRefGoogle Scholar
  9. 9.
    European Society of Radiology (ESR). ESR position paper on imaging biobanks. Insights Imaging. 2015;6:403–10.CrossRefGoogle Scholar
  10. 10.
    Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. 2014. arXiv:1406.2661.Google Scholar
  11. 11.
    Thaler SL. US Patent, 07454388, Device for the autonomous bootstrapping of useful information, 11/18/2008.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Angel Alberich-Bayarri
    • 1
    • 2
    Email author
  • Ana Jiménez Pastor
    • 2
  • Rafael López González
    • 2
  • Fabio García Castro
    • 2
  1. 1.Biomedical Imaging Research Group (GIBI2^30)La Fe Health Research InstituteValenciaSpain
  2. 2.Quantitative Imaging Biomarkers in Medicine (QUIBIM S.L.)ValenciaSpain

Personalised recommendations